The interpretability of medical image analysis models is considered a key research field. We use a dataset of eye-tracking data from five radiologists to compare the outputs of interpretability methods and the heatmaps representing where radiologists looked. We conduct a class-independent analysis of the saliency maps generated by two methods selected from the literature: Grad-CAM and attention maps from an attention-gated model. For the comparison, we use shuffled metrics, which avoid biases from fixation locations. We achieve scores comparable to an interobserver baseline in one shuffled metric, highlighting the potential of saliency maps from Grad-CAM to mimic a radiologist's attention over an image. We also divide the dataset into subsets to evaluate in which cases similarities are higher.
@article{arxiv.2112.11716,
title = {Comparing radiologists' gaze and saliency maps generated by interpretability methods for chest x-rays},
author = {Ricardo Bigolin Lanfredi and Ambuj Arora and Trafton Drew and Joyce D. Schroeder and Tolga Tasdizen},
journal= {arXiv preprint arXiv:2112.11716},
year = {2023}
}
Comments
This paper was presented as an Extended Abstract at the Gaze Meets ML 2022 Workshop, a NeurIPS 2022 workshop